linux/net
Neal Cardwell 032ee42369 tcp: helpers to mitigate ACK loops by rate-limiting out-of-window dupacks
Helpers for mitigating ACK loops by rate-limiting dupacks sent in
response to incoming out-of-window packets.

This patch includes:

- rate-limiting logic
- sysctl to control how often we allow dupacks to out-of-window packets
- SNMP counter for cases where we rate-limited our dupack sending

The rate-limiting logic in this patch decides to not send dupacks in
response to out-of-window segments if (a) they are SYNs or pure ACKs
and (b) the remote endpoint is sending them faster than the configured
rate limit.

We rate-limit our responses rather than blocking them entirely or
resetting the connection, because legitimate connections can rely on
dupacks in response to some out-of-window segments. For example, zero
window probes are typically sent with a sequence number that is below
the current window, and ZWPs thus expect to thus elicit a dupack in
response.

We allow dupacks in response to TCP segments with data, because these
may be spurious retransmissions for which the remote endpoint wants to
receive DSACKs. This is safe because segments with data can't
realistically be part of ACK loops, which by their nature consist of
each side sending pure/data-less ACKs to each other.

The dupack interval is controlled by a new sysctl knob,
tcp_invalid_ratelimit, given in milliseconds, in case an administrator
needs to dial this upward in the face of a high-rate DoS attack. The
name and units are chosen to be analogous to the existing analogous
knob for ICMP, icmp_ratelimit.

The default value for tcp_invalid_ratelimit is 500ms, which allows at
most one such dupack per 500ms. This is chosen to be 2x faster than
the 1-second minimum RTO interval allowed by RFC 6298 (section 2, rule
2.4). We allow the extra 2x factor because network delay variations
can cause packets sent at 1 second intervals to be compressed and
arrive much closer.

Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-02-08 01:03:12 -08:00
..
6lowpan net/6lowpan: Remove FSF address from GPL statement. 2014-12-05 12:43:04 +01:00
9p 9p/trans_virtio: enable VQs early 2014-10-15 10:25:04 +10:30
802
8021q vlan: advertise link netns via netlink 2015-01-23 17:51:15 -08:00
appletalk new helper: memcpy_from_msg() 2014-11-24 04:28:48 -05:00
atm put iov_iter into msghdr 2014-12-09 16:29:03 -05:00
ax25 new helper: memcpy_from_msg() 2014-11-24 04:28:48 -05:00
batman-adv batman-adv: Kconfig, Add missing DEBUG_FS dependency 2015-01-07 22:17:11 +01:00
bluetooth Bluetooth: Fix potential NULL dereference 2015-02-03 09:02:12 +01:00
bridge bridge: add missing bridge port check for offloads 2015-02-07 22:49:47 -08:00
caif caif: remove wrong dev_net_set() call 2015-01-29 14:20:02 -08:00
can netlink: make nlmsg_end() and genlmsg_end() void 2015-01-18 01:03:45 -05:00
ceph libceph: fix sparse endianness warnings 2015-01-08 20:36:57 +03:00
core Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-02-05 14:33:28 -08:00
dcb dcbnl : Disable software interrupts before taking dcb_lock 2014-11-16 14:50:52 -05:00
dccp net: introduce helper macro for_each_cmsghdr 2014-12-10 22:41:55 -05:00
decnet netlink: Fix bugs in nlmsg_end() conversions. 2015-01-18 23:36:08 -05:00
dns_resolver Merge commit 'v3.16' into next 2014-10-01 00:44:04 +10:00
dsa net: dsa: set slave MII bus PHY mask 2015-01-25 16:00:54 -08:00
ethernet net: Add Transparent Ethernet Bridging GRO support. 2015-01-02 15:46:41 -05:00
hsr
ieee802154 netlink: make nlmsg_end() and genlmsg_end() void 2015-01-18 01:03:45 -05:00
ipv4 tcp: helpers to mitigate ACK loops by rate-limiting out-of-window dupacks 2015-02-08 01:03:12 -08:00
ipv6 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-02-05 14:33:28 -08:00
ipx switch ipxrtr_route_packet() from iovec to msghdr 2014-11-24 04:28:49 -05:00
irda irda: use msecs_to_jiffies for conversions 2015-01-30 18:08:25 -08:00
iucv net: introduce helper macro for_each_cmsghdr 2014-12-10 22:41:55 -05:00
key new helper: memcpy_from_msg() 2014-11-24 04:28:48 -05:00
l2tp netlink: make nlmsg_end() and genlmsg_end() void 2015-01-18 01:03:45 -05:00
lapb lapb: move EXPORT_SYMBOL after functions. 2014-10-24 15:51:42 -04:00
llc net: llc: use correct size for sysctl timeout entries 2015-01-25 00:23:21 -08:00
mac80211 Last round of updates for net-next: 2015-02-04 14:57:45 -08:00
mac802154 mac802154: fix kbuild test robot warning 2015-01-03 01:51:51 +01:00
mpls net: mark some potential candidates __read_mostly 2015-01-30 17:58:39 -08:00
netfilter Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-02-05 14:33:28 -08:00
netlabel netlabel: Less function calls in netlbl_mgmt_add_common() after error detection 2015-02-03 16:22:13 -08:00
netlink Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-02-05 14:33:28 -08:00
netrom new helper: memcpy_from_msg() 2014-11-24 04:28:48 -05:00
nfc NFC: nci: Move NFCEE discovery logic 2015-02-04 09:15:18 +01:00
openvswitch openvswitch: Initialize unmasked key and uid len 2015-02-08 00:51:14 -08:00
packet netlink: make nlmsg_end() and genlmsg_end() void 2015-01-18 01:03:45 -05:00
phonet phonet netlink: allow multiple messages per skb in route dump 2015-01-19 16:20:17 -05:00
rds rds: Make rds_message_copy_from_user() return 0 on success. 2015-02-07 22:41:56 -08:00
rfkill Last round of updates for net-next: 2015-02-04 14:57:45 -08:00
rose new helper: memcpy_from_msg() 2014-11-24 04:28:48 -05:00
rxrpc Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-02-04 20:46:55 -08:00
sched Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-02-05 14:33:28 -08:00
sctp Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-02-05 14:33:28 -08:00
sunrpc rpc: fix xdr_truncate_encode to handle buffer ending on page boundary 2015-01-07 14:03:58 -05:00
switchdev swdevice: add new apis to set and del bridge port attributes 2015-02-01 23:16:34 -08:00
tipc tipc: eliminate race condition at multicast reception 2015-02-05 16:00:03 -08:00
unix net: remove sock_iocb 2015-01-28 23:15:07 -08:00
vmw_vsock vmci: propagate msghdr all way down to __qp_memcpy_to_queue() 2015-02-04 01:34:14 -05:00
wimax wimax: convert printk to pr_foo() 2014-10-07 20:28:44 -04:00
wireless Last round of updates for net-next: 2015-02-04 14:57:45 -08:00
x25 new helper: memcpy_from_msg() 2014-11-24 04:28:48 -05:00
xfrm netlink: make nlmsg_end() and genlmsg_end() void 2015-01-18 01:03:45 -05:00
compat.c put iov_iter into msghdr 2014-12-09 16:29:03 -05:00
Kconfig net: introduce generic switch devices support 2014-12-02 20:01:20 -08:00
Makefile Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2014-12-16 15:53:03 -08:00
socket.c net: switch sockets to ->read_iter/->write_iter 2015-02-04 01:34:15 -05:00
sysctl_net.c